commercial

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Commercial production with genmedia

使用genmedia进行商业内容制作

Use this skill when the user wants advertising, product, brand, or e-commerce media. Load the reference files when you need prompt patterns or category examples:

```
references/prompt-patterns.md
```
```
references/workflows.md
```
```
references/examples.md
```

Load

model-routing

alongside this skill for default endpoint choices.

Keep the output production-focused. Do not add inflated marketing language, unsupported claims, fake text in the image, or em dashes.

当用户需要广告、产品、品牌或电商相关媒体内容时，使用此技能。当你需要提示词模板或分类示例时，加载参考文件：

```
references/prompt-patterns.md
```
```
references/workflows.md
```
```
references/examples.md
```

搭配

model-routing

使用此技能，以获取默认的端点选项。

输出内容需聚焦于生产需求。请勿添加夸大的营销话术、无依据的声明、图片中的虚假文字或长破折号。

Inputs to collect

需要收集的输入信息

Only ask when the answer cannot be inferred from the task or the source files.

Product: exact product name, category, material, color, scale, logo rules.
Goal: hero shot, PDP image, ad creative, motion reveal, demo, UGC, lifestyle.
Platform: square, vertical, landscape, banner, transparent background, print.
Brand: premium, playful, clinical, athletic, minimal, natural, technical.
Source media: product packshot, logo, reference scene, prior generated asset.
Constraints: preserve packaging, avoid new labels, no fake readable copy.
Model preference: use
```
model-routing
```
defaults unless the user names a model or the job is unusually expensive.

仅当无法从任务或源文件中推断出答案时才询问。

产品：准确的产品名称、类别、材质、颜色、尺寸比例、logo规范。
目标：主图展示、商品详情页图片、广告创意、动态展示、演示视频、用户生成内容（UGC）、生活风格场景。
平台规格：方形、竖版、横版、横幅、透明背景、印刷格式。
品牌风格：高端、活泼、专业严谨、运动风、极简、自然、科技感。
源媒体：产品实拍图、logo、参考场景、之前生成的素材。
约束条件：保留包装、避免新增标签、无虚假可读文字。
模型偏好：除非用户指定模型或任务成本异常高昂，否则使用
```
model-routing
```
的默认设置。

Genmedia workflow

Genmedia工作流程

Start from routed endpoint IDs.

bash

genmedia models --endpoint_id openai/gpt-image-2 --json
genmedia models --endpoint_id fal-ai/nano-banana-pro/edit --json
genmedia models --endpoint_id fal-ai/nano-banana-2 --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json

Use text search only as fallback discovery for a missing utility or unsupported role:

bash

genmedia models "background removal product image" --json
genmedia docs "commercial product image generation" --json

Inspect the selected endpoint before running.

bash

genmedia schema <endpoint_id> --json
genmedia pricing <endpoint_id> --json

Upload every local or remote reference file.

bash

genmedia upload ./product.png --json
genmedia upload ./logo.png --json

Run still-image jobs synchronously when they are quick.

bash

genmedia run <endpoint_id> \
  --prompt "<commercial prompt>" \
  --image_url "<uploaded product url if supported>" \
  --download "./outputs/commercial/{request_id}_{index}.{ext}" \
  --json

Run video jobs async and download from

status

bash

genmedia run <endpoint_id> \
  --prompt "<motion prompt>" \
  --image_url "<uploaded hero frame if supported>" \
  --async \
  --json

genmedia status <endpoint_id> <request_id> \
  --download "./outputs/commercial/{request_id}_{index}.{ext}" \
  --json

Use schema fields exactly. Do not pass guessed flags. If the model uses
```
image_urls
```
,
```
reference_image_url
```
,
```
aspect_ratio
```
,
```
duration
```
,
```
seed
```
, or another name, mirror that schema.

从路由后的端点ID开始。

bash

genmedia models --endpoint_id openai/gpt-image-2 --json
genmedia models --endpoint_id fal-ai/nano-banana-pro/edit --json
genmedia models --endpoint_id fal-ai/nano-banana-2 --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json

仅在找不到适用工具或不支持相关功能时，才使用文本搜索作为备选方案：

bash

genmedia models "background removal product image" --json
genmedia docs "commercial product image generation" --json

在运行前检查所选端点。

bash

genmedia schema <endpoint_id> --json
genmedia pricing <endpoint_id> --json

上传所有本地或远程参考文件。

bash

genmedia upload ./product.png --json
genmedia upload ./logo.png --json

对于快速完成的静态图片任务，同步运行。

bash

genmedia run <endpoint_id> \
  --prompt "<commercial prompt>" \
  --image_url "<uploaded product url if supported>" \
  --download "./outputs/commercial/{request_id}_{index}.{ext}" \
  --json

异步运行视频任务，并通过

status

命令下载结果。

bash

genmedia run <endpoint_id> \
  --prompt "<motion prompt>" \
  --image_url "<uploaded hero frame if supported>" \
  --async \
  --json

genmedia status <endpoint_id> <request_id> \
  --download "./outputs/commercial/{request_id}_{index}.{ext}" \
  --json

严格使用schema字段。请勿传递猜测的参数。如果模型使用
```
image_urls
```
、
```
reference_image_url
```
、
```
aspect_ratio
```
、
```
duration
```
、
```
seed
```
或其他命名参数，请严格遵循其schema。

Prompt build order

提示词构建顺序

Write prompts in this order so commercial intent stays clear:

Product invariant: exact object, material, color, packaging, scale.
Commercial role: hero image, PDP image, launch teaser, demo shot, social ad.
Setting: surface, background, props, environment, distance from product.
Lighting: softbox, strip light, rim light, backlight, caustics, practicals.
Camera: angle, focal length feel, macro, depth of field, motion if video.
Composition: centered, negative space, safe zone, text-free area, platform.
Brand tone: premium, clean, clinical, bold, energetic, warm, editorial.
Guardrails: preserve logo and packaging, no extra text, no distorted labels.

Do not promise claims like "best", "clinically proven", "50 percent faster", or celebrity endorsements unless the user provides that copy.

按照以下顺序编写提示词，确保商业意图清晰：

产品固定信息：准确的物品、材质、颜色、包装、尺寸比例。
商业用途：主图、商品详情页图片、发布预告、演示镜头、社交广告。
场景设置：表面、背景、道具、环境、与产品的距离。
灯光：柔光箱、条形灯、轮廓灯、背光、焦散效果、实用光源。
相机：角度、焦距质感、微距、景深、视频动态效果。
构图：居中、留白、安全区域、无文字区域、平台适配。
品牌调性：高端、简洁、专业严谨、大胆、活力、温暖、编辑风格。
防护规则：保留logo和包装、无额外文字、无变形标签。

除非用户提供相关文案，否则请勿做出“最佳”“临床验证”“快50%”或名人代言等承诺。

Model routing

模型路由

Text-heavy ads, labels, posters, UI mockups, packaging copy, and infographics: use
```
openai/gpt-image-2
```
at
```
quality=high
```
. Prefer 2K or 4K when the final must carry small readable details. Treat this as expensive.
Premium realistic stills: use
```
openai/gpt-image-2
```
.

Premium stylized stills: use

openai/gpt-image-2

, then

fal-ai/nano-banana-pro

, then

fal-ai/nano-banana-2

Fast draft stills: use
```
fal-ai/flux-2/klein/9b
```
.

Image edits: use

fal-ai/nano-banana-pro/edit

, then

openai/gpt-image-2/edit

, then

fal-ai/bytedance/seedream/v5/lite/edit

Product fidelity: use
```
fal-ai/nano-banana-pro
```
,
```
fal-ai/nano-banana-2
```
, or
```
fal-ai/bytedance/seedream/v5/lite/text-to-image
```
; use the matching edit endpoint when a product reference image exists.
Product reveal video: create or upload a strong hero frame, then use
```
bytedance/seedance-2.0/image-to-video
```
for final quality.

Fast or lower-cost video draft: use

xai/grok-imagine-video/image-to-video

xai/grok-imagine-video/text-to-video

E-commerce batch: keep the same prompt skeleton and vary only background, crop, lighting, or platform format.
Text overlays: generate with empty safe space. Add final text in a design or editing tool unless the selected model is explicitly good at typography.
Background removal or cleanup: search for background removal, segmentation, inpainting, or product editing models and inspect their schemas.
Final delivery: use
```
--download
```
with
```
{request_id}
```
and
```
{index}
```
.

包含大量文字的广告、标签、海报、UI原型、包装文案以及信息图表：使用
```
openai/gpt-image-2
```
并设置
```
quality=high
```
。当最终内容需要承载小尺寸可读细节时，优先选择2K或4K分辨率。注意此选项成本较高。
高端写实静态图：使用
```
openai/gpt-image-2
```
。
高端风格化静态图：优先使用
```
openai/gpt-image-2
```
，其次是
```
fal-ai/nano-banana-pro
```
，最后是
```
fal-ai/nano-banana-2
```
。
快速草稿静态图：使用
```
fal-ai/flux-2/klein/9b
```
。

图片编辑：优先使用

fal-ai/nano-banana-pro/edit

，其次是

openai/gpt-image-2/edit

，最后是

fal-ai/bytedance/seedream/v5/lite/edit

。

产品还原度：使用
```
fal-ai/nano-banana-pro
```
、
```
fal-ai/nano-banana-2
```
或
```
fal-ai/bytedance/seedream/v5/lite/text-to-image
```
；当有产品参考图时，使用对应的编辑端点。
产品发布展示视频：创建或上传高质量主图帧，然后使用
```
bytedance/seedance-2.0/image-to-video
```
获取最终品质。

快速或低成本视频草稿：使用

xai/grok-imagine-video/image-to-video

或

xai/grok-imagine-video/text-to-video

。

电商批量内容：保持提示词框架一致，仅更改背景、裁剪、灯光或平台格式。
文字叠加：生成时预留空白安全区域。除非所选模型明确擅长排版，否则在设计或编辑工具中添加最终文字。
背景移除或清理：搜索背景移除、分割、修复或产品编辑类模型，并检查其schema。
最终交付：使用
```
--download
```
参数并搭配
```
{request_id}
```
和
```
{index}
```
。

Quality bar

质量标准

Before returning, check:

Product shape, logo, material, and color are not invented or distorted.
The composition leaves enough room for platform crop and optional copy.
Background props support the product and do not compete with it.
Any generated text is absent or intentionally controlled.
Lighting makes sense for the product material.
Output paths are from
```
downloaded_files[]
```
, not manually curled URLs.

If the result misses product fidelity, switch from text-only generation to a reference or edit workflow before retrying.

返回结果前，请检查：

产品形状、logo、材质和颜色未被篡改或失真。
构图为平台裁剪和可选文案预留了足够空间。
背景道具为产品增色，而非喧宾夺主。
生成的文字不存在或处于可控状态。
灯光符合产品材质特性。
输出路径来自
```
downloaded_files[]
```
，而非手动拼接的URL。

如果结果产品还原度不足，请在重试前从纯文本生成切换为参考图或编辑工作流。